Search papers, labs, and topics across Lattice.
3
0
5
High-quality mobile video generation is now possible with a 5B-parameter model, challenging the notion that smaller models are necessary for mobile applications.
Shrinking LLM reasoning for mobile devices is now possible: LoRA adapters, RL-based budget forcing, and KV-cache tricks let Qwen2.5-7B reason efficiently on-device.
Quantization error isn't just about concentrating weights, it's also about aligning them with activations, and a simple transform can exploit this to boost 4-bit LLM performance.
